{"id":"https://openalex.org/W4408345851","doi":"https://doi.org/10.1109/icassp49660.2025.10889906","title":"Binary Representation Learning for Discriminative Acoustic Unit Discovery","display_name":"Binary Representation Learning for Discriminative Acoustic Unit Discovery","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345851","doi":"https://doi.org/10.1109/icassp49660.2025.10889906"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010655034","display_name":"Rui Niu","orcid":"https://orcid.org/0000-0002-8599-6374"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Niu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333004","display_name":"Jie Chen","orcid":"https://orcid.org/0000-0003-2306-8860"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Chen","raw_affiliation_strings":["Tencent,Youtu Lab,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Youtu Lab,Beijing,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101487902","display_name":"Long Ma","orcid":"https://orcid.org/0000-0002-8357-424X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Ma","raw_affiliation_strings":["Tencent,Youtu Lab,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Youtu Lab,Beijing,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020605377","display_name":"Changhe Song","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changhe Song","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113820804","display_name":"Weihao Wu","orcid":"https://orcid.org/0009-0006-4466-1080"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihao Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100667025","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0002-6527-5502"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03591247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9866999983787537,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9866999983787537,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9828000068664551,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8061469793319702},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6649050116539001},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5647931694984436},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.49191999435424805},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46353840827941895},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.46282893419265747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46202123165130615},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4187150299549103},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36479613184928894},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33934086561203003},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13775262236595154},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.06535729765892029}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8061469793319702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6649050116539001},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5647931694984436},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.49191999435424805},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46353840827941895},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.46282893419265747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46202123165130615},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4187150299549103},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36479613184928894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33934086561203003},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13775262236595154},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.06535729765892029},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2065927558","https://openalex.org/W2133665775","https://openalex.org/W2347098582","https://openalex.org/W2463237750","https://openalex.org/W2592866267","https://openalex.org/W2719865699","https://openalex.org/W2752796333","https://openalex.org/W2927191280","https://openalex.org/W2940544976","https://openalex.org/W2972359262","https://openalex.org/W2972964185","https://openalex.org/W3009806461","https://openalex.org/W3024869864","https://openalex.org/W3035524453","https://openalex.org/W3095361818","https://openalex.org/W3096216486","https://openalex.org/W3100270690","https://openalex.org/W3114632476","https://openalex.org/W3181704441","https://openalex.org/W3188087362","https://openalex.org/W3197659778","https://openalex.org/W3197974236","https://openalex.org/W3198680251","https://openalex.org/W3198782837","https://openalex.org/W4210885000","https://openalex.org/W4390887450","https://openalex.org/W6675022971","https://openalex.org/W6734901337","https://openalex.org/W6772349387","https://openalex.org/W6774314701","https://openalex.org/W6779997284","https://openalex.org/W6783867762","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W3119773509","https://openalex.org/W3208297503","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611"],"abstract_inverted_index":{"Acoustic":[0],"Unit":[1],"Discovery":[2],"(AUD)":[3],"aims":[4],"to":[5,48,81],"obtain":[6],"phoneme-like":[7],"units":[8],"that":[9,42,66,89],"preserve":[10],"linguistically":[11],"significant":[12],"information":[13,50],"while":[14],"removing":[15],"paralinguistic":[16,49],"details.":[17],"Although":[18],"Contrastive":[19],"Predictive":[20],"Coding":[21],"(CPC)":[22],"has":[23],"emerged":[24],"as":[25],"a":[26,63,68],"leading":[27],"self-supervised":[28],"representation":[29,71],"learning":[30,77],"method":[31,91],"for":[32],"this":[33],"task,":[34],"CPC-based":[35],"methods":[36],"still":[37],"suffer":[38],"from":[39],"the":[40,43,56,83],"limitation":[41],"learned":[44],"representations":[45],"are":[46],"susceptible":[47],"and":[51,73,98],"less":[52],"discriminative.":[53],"Inspired":[54],"by":[55],"theory":[57],"of":[58],"distinctive":[59],"features,":[60],"we":[61],"propose":[62],"new":[64],"approach":[65],"builds":[67],"binary":[69,75,101],"discriminative":[70,100],"space":[72],"employs":[74],"contrastive":[76],"based":[78],"on":[79],"CPC":[80],"tackle":[82],"aforementioned":[84],"issues.":[85],"Experimental":[86],"results":[87,94],"show":[88],"our":[90],"achieves":[92],"better":[93],"in":[95],"AUD":[96],"task":[97],"produces":[99],"representations.":[102]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}